arXiv subjects

Sahil Shah

Publications and source records attributed to Sahil Shah.

30 records · Page 2Linked to original sources

arXiv2025

Real-Time Privacy Preservation for Robot Visual Perception

Many robots (e.g., iRobot's Roomba) operate based on visual observations from live video streams, and such observations may inadvertently include privacy-sensitive objects, such as personal identifiers. Existing approaches for preserving privacy rely on deep learning models, differential privacy, or cryptography. They lack guarantees for the complete concealment of all sensitive objects. Guaranteeing concealment requires post-processing techniques and thus is inadequate for real-time video streams. We develop a method for privacy-constrained video streaming, PCVS, that conceals sensitive objects within real-time video streams. PCVS takes a logical specification constraining the existence of privacy-sensitive objects, e.g., never show faces when a person exists. It uses a detection model to evaluate the existence of these objects in each incoming frame. Then, it blurs out a subset of objects such that the existence of the remaining objects satisfies the specification. We then propose a conformal prediction approach to (i) establish a theoretical lower bound on the probability of the existence of these objects in a sequence of frames satisfying the specification and (ii) update the bound with the arrival of each subsequent frame. Quantitative evaluations show that PCVS achieves over 95 percent specification satisfaction rate in multiple datasets, significantly outperforming other methods. The satisfaction rate is consistently above the theoretical bounds across all datasets, indicating that the established bounds hold. Additionally, we deploy PCVS on robots in real-time operation and show that the robots operate normally without being compromised when PCVS conceals objects.

cs.CV↗

arXiv2025

Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification

Recent advancements in text-to-video models such as Sora, Gen-3, MovieGen, and CogVideoX are pushing the boundaries of synthetic video generation, with adoption seen in fields like robotics, autonomous driving, and entertainment. As these models become prevalent, various metrics and benchmarks have emerged to evaluate the quality of the generated videos. However, these metrics emphasize visual quality and smoothness, neglecting temporal fidelity and text-to-video alignment, which are crucial for safety-critical applications. To address this gap, we introduce NeuS-V, a novel synthetic video evaluation metric that rigorously assesses text-to-video alignment using neuro-symbolic formal verification techniques. Our approach first converts the prompt into a formally defined Temporal Logic (TL) specification and translates the generated video into an automaton representation. Then, it evaluates the text-to-video alignment by formally checking the video automaton against the TL specification. Furthermore, we present a dataset of temporally extended prompts to evaluate state-of-the-art video generation models against our benchmark. We find that NeuS-V demonstrates a higher correlation by over 5x with human evaluations when compared to existing metrics. Our evaluation further reveals that current video generation models perform poorly on these temporally complex prompts, highlighting the need for future work in improving text-to-video generation capabilities.

cs.CV↗

arXiv2025

Acoustic Analysis of Uneven Blade Spacing and Toroidal Geometry for Reducing Propeller Annoyance

Unmanned aerial vehicles (UAVs) are becoming more commonly used in populated areas, raising concerns about noise pollution generated from their propellers. This study investigates the acoustic performance of unconventional propeller designs, specifically toroidal and uneven-blade spaced propellers, for their potential in reducing psychoacoustic annoyance. Our experimental results show that these designs noticeably reduced acoustic characteristics associated with noise annoyance.

physics.flu-dyn↗

arXiv2024

Towards Neuro-Symbolic Video Understanding

The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems. While state-of-the-art foundation models, like VideoLLaMA and ViCLIP, are proficient in short-term semantic understanding, they surprisingly fail at long-term reasoning across frames. A key reason for this failure is that they intertwine per-frame perception and temporal reasoning into a single deep network. Hence, decoupling but co-designing semantic understanding and temporal reasoning is essential for efficient scene identification. We propose a system that leverages vision-language models for semantic understanding of individual frames but effectively reasons about the long-term evolution of events using state machines and temporal logic (TL) formulae that inherently capture memory. Our TL-based reasoning improves the F1 score of complex event identification by 9-15% compared to benchmarks that use GPT4 for reasoning on state-of-the-art self-driving datasets such as Waymo and NuScenes.

cs.CV↗

arXiv2023

Modeling and Analysis of Analog Non-Volatile Devices for Compute-In-Memory Applications

This paper introduces a novel simulation tool for analyzing and training neural network models tailored for compute-in-memory hardware. The tool leverages physics-based device models to enable the design of neural network models and their parameters that are more hardware-accurate. The initial study focused on modeling a CMOS-based floating-gate transistor and memristor device using measurement data from a fabricated device. Additionally, the tool incorporates hardware constraints, such as the dynamic range of data converters, and allows users to specify circuit-level constraints. A case study using the MNIST dataset and LeNet-5 architecture demonstrates the tool's capability to estimate area, power, and accuracy. The results showcase the potential of the proposed tool to optimize neural network models for compute-in-memory hardware.

cs.AR↗

arXiv2021

On the Robustness of Human Pose Estimation

This paper provides a comprehensive and exhaustive study of adversarial attacks on human pose estimation models and the evaluation of their robustness. Besides highlighting the important differences between well-studied classification and human pose-estimation systems w.r.t. adversarial attacks, we also provide deep insights into the design choices of pose-estimation systems to shape future work. We benchmark the robustness of several 2D single person pose-estimation architectures trained on multiple datasets, MPII and COCO. In doing so, we also explore the problem of attacking non-classification networks including regression based networks, which has been virtually unexplored in the past. \par We find that compared to classification and semantic segmentation, human pose estimation architectures are relatively robust to adversarial attacks with the single-step attacks being surprisingly ineffective. Our study shows that the heatmap-based pose-estimation models are notably robust than their direct regression-based systems and that the systems which explicitly model anthropomorphic semantics of human body fare better than their other counterparts. Besides, targeted attacks are more difficult to obtain than un-targeted ones and some body-joints are easier to fool than the others. We present visualizations of universal perturbations to facilitate unprecedented insights into their workings on pose-estimation. Additionally, we show them to generalize well across different networks. Finally we perform a user study about perceptibility of these examples.

cs.CV↗

arXiv2021

Eye: Program Visualizer for CS2

In recent years, programming has witnessed a shift towards using standard libraries as a black box. However, there has not been a synchronous development of tools that can help demonstrate the working of such libraries in general programs, which poses an impediment to improved learning outcomes and makes debugging exasperating. We introduce Eye, an interactive pedagogical tool that visualizes a program's execution as it runs. It demonstrates properties and usage of data structures in a general environment, thereby helping in learning, logical debugging, and code comprehension. Eye provides a comprehensive overview at each stage during run time including the execution stack and the state of data structures. The modular implementation allows for extension to other languages and modification of the graphics as desired. Eye opens up a gateway for CS2 students to more easily understand myriads of programs that are available on online programming websites, lowering the barrier towards self-learning of coding. It expands the scope of visualizing data structures from standard algorithms to general cases, benefiting both teachers as well as programmers who face issues in debugging. Line by line interpreting allows Eye to describe the execution and not only the current state. We also conduct experiments to evaluate the efficacy of Eye for debugging and comprehending a new piece of code. Our findings show that it becomes faster and less frustrating to debug certain problems using this tool, and also makes understanding new code a much more pleasant experience.

cs.CY↗

arXiv2020

NLP Service APIs and Models for Efficient Registration of New Clients

State-of-the-art NLP inference uses enormous neural architectures and models trained for GPU-months, well beyond the reach of most consumers of NLP. This has led to one-size-fits-all public API-based NLP service models by major AI companies, serving large numbers of clients. Neither (hardware deficient) clients nor (heavily subscribed) servers can afford traditional fine tuning. Many clients own little or no labeled data. We initiate a study of adaptation of centralized NLP services to clients, and present one practical and lightweight approach. Each client uses an unsupervised, corpus-based sketch to register to the service. The server uses an auxiliary network to map the sketch to an abstract vector representation, which then informs the main labeling network. When a new client registers with its sketch, it gets immediate accuracy benefits. We demonstrate the success of the proposed architecture using sentiment labeling, NER, and predictive language modeling

cs.LG↗

arXiv2020

Lower Bounds for Policy Iteration on Multi-action MDPs

Policy Iteration (PI) is a classical family of algorithms to compute an optimal policy for any given Markov Decision Problem (MDP). The basic idea in PI is to begin with some initial policy and to repeatedly update the policy to one from an improving set, until an optimal policy is reached. Different variants of PI result from the (switching) rule used for improvement. An important theoretical question is how many iterations a specified PI variant will take to terminate as a function of the number of states $n$ and the number of actions $k$ in the input MDP. While there has been considerable progress towards upper-bounding this number, there are fewer results on lower bounds. In particular, existing lower bounds primarily focus on the special case of $k = 2$ actions. We devise lower bounds for $k \geq 3$. Our main result is that a particular variant of PI can take $Ω(k^{n/2})$ iterations to terminate. We also generalise existing constructions on $2$-action MDPs to scale lower bounds by a factor of $k$ for some common deterministic variants of PI, and by $\log(k)$ for corresponding randomised variants.

cs.LG↗

arXiv2020

An India-specific Compartmental Model for Covid-19: Projections and Intervention Strategies by Incorporating Geographical, Infrastructural and Response Heterogeneity

We present a compartmental meta-population model for the spread of Covid-19 in India. Our model simulates populations at a district or state level using an epidemiological model that is appropriate to Covid-19. Different districts are connected by a transportation matrix developed using available census data. We introduce uncertainties in the testing rates into the model that takes into account the disparate responses of the different states to the epidemic and also factors in the state of the public healthcare system. Our model allows us to generate qualitative projections of Covid-19 spread in India, and further allows us to investigate the effects of different proposed interventions. By building in heterogeneity at geographical and infrastructural levels and in local responses, our model aims to capture some of the complexity of epidemiological modeling appropriate to a diverse country such as India.

q-bio.PE↗

arXiv2020

Worst-Case Optimal Covering of Rectangles by Disks

We provide the solution for a fundamental problem of geometric optimization by giving a complete characterization of worst-case optimal disk coverings of rectangles: For any $λ\geq 1$, the critical covering area $A^*(λ)$ is the minimum value for which any set of disks with total area at least $A^*(λ)$ can cover a rectangle of dimensions $λ\times 1$. We show that there is a threshold value $λ_2 = \sqrt{\sqrt{7}/2 - 1/4} \approx 1.035797\ldots$, such that for $λ<λ_2$ the critical covering area $A^*(λ)$ is $A^*(λ)=3π\left(\frac{λ^2}{16} +\frac{5}{32} + \frac{9}{256λ^2}\right)$, and for $λ\geq λ_2$, the critical area is $A^*(λ)=π(λ^2+2)/4$; these values are tight. For the special case $λ=1$, i.e., for covering a unit square, the critical covering area is $\frac{195π}{256}\approx 2.39301\ldots$. The proof uses a careful combination of manual and automatic analysis, demonstrating the power of the employed interval arithmetic technique.

cs.CG↗

arXiv2014

Network Methods for Pathway Analysis of Genomic Data

Rapid advances in high-throughput technologies have led to considerable interest in analyzing genome-scale data in the context of biological pathways, with the goal of identifying functional systems that are involved in a given phenotype. In the most common approaches, biological pathways are modeled as simple sets of genes, neglecting the network of interactions comprising the pathway and treating all genes as equally important to the pathway's function. Recently, a number of new methods have been proposed to integrate pathway topology in the analyses, harnessing existing knowledge and enabling more nuanced models of complex biological systems. However, there is little guidance available to researches choosing between these methods. In this review, we discuss eight topology-based methods, comparing their methodological approaches and appropriate use cases. In addition, we present the results of the application of these methods to a curated set of ten gene expression profiling studies using a common set of pathway annotations. We report the computational efficiency of the methods and the consistency of the results across methods and studies to help guide users in choosing a method. We also discuss the challenges and future outlook for improved network analysis methodologies.

q-bio.QM↗